© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 89989
    Prev
    Next
    INDEX
    Explanations

    .com/

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_23_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    >\
    0.35
    omiast
    0.32
    🧿
    0.31
     Yayın
    0.31
    ḿ
    0.31
     Krav
    0.31
    msub
    0.30
    𝚂
    0.30
     possèdent
    0.30
     ,\
    0.29
    POSITIVE LOGITS
    íme
    0.35
     reporters
    0.30
     enforce
    0.29
    濟
    0.29
     petty
    0.29
    icheskoj
    0.29
    ógico
    0.28
     discours
    0.28
    кової
    0.28
     explic
    0.27
    Activations Density 0.002%

    No Known Activations